Search Results for author:
Found 91 papers, 39 papers with code
NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results.
Low-Light Image Enhancement using Event-Based Illumination Estimation
Low-light image enhancement (LLIE) aims to improve the visibility of images captured in poorly lit environments.
Exploration-Driven Generative Interactive Environments
To this end, we annotate the behavior and controls of 974 virtual environments - a dataset that we name RetroAct.
Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness
We then introduce a robustness benchmark that evaluates MMSS models under three scenarios: Entire-Missing Modality (EMM), Random-Missing Modality (RMM), and Noisy Modality (NM).
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
In order to power the proposed methods, we introduce SceneSplat-7K, the first large-scale 3DGS dataset for indoor scenes, comprising of 6868 scenes derived from 7 established datasets like ScanNet, Matterport3D, etc.
Dream to Drive: Model-Based Vehicle Control Using Analytic World Models
Differentiable simulators have recently shown great promise for training autonomous vehicle controllers.
CityLoc: 6DoF Pose Distributional Localization for Text Descriptions in Large-Scale Scenes with Gaussian Representation
Localizing textual descriptions within large-scale 3D scenes presents inherent ambiguities, such as identifying all traffic lights in a city.
Understanding the World's Museums through Vision-Language Reasoning
In this work, we facilitate such reasoning by (a) collecting and curating a large-scale dataset of 65M images and 200M question-answer pairs in the standard museum catalog format for exhibits from all around the world; (b) training large vision-language models on the collected dataset; (c) benchmarking their ability on five visual question answering tasks.
Holistic Understanding of 3D Scenes as Universal Scene Description
In this work, we address this shortcoming and introduce (1) an expertly curated dataset in the Universal Scene Description (USD) format, featuring high-quality manual annotations, for instance, segmentation and articulation on 280 indoor scenes; (2) a learning-based model together with a novel baseline capable of predicting part segmentation along with a full specification of motion attributes, including motion type, articulated and interactable parts, and motion parameters; (3) a benchmark serving to compare upcoming methods for the task at hand.
Occam's LGS: A Simple Approach for Language Gaussian Splatting
A major reason for the success of 3DGS is its simplicity of representing a scene with a set of Gaussians, which makes it easy to interpret and adapt.
ObjectRelator: Enabling Cross-View Object Relation Understanding in Ego-Centric and Exo-Centric Videos
In this paper, we focus on the Ego-Exo Object Correspondence task, an emerging challenge in the field of computer vision that aims to map objects across ego-centric and exo-centric views.
Complexity Experts are Task-Discriminative Learners for Any Image Restoration
To address this, we introduce ``complexity experts" -- flexible expert blocks with varying computational complexity and receptive fields.
Ranked #2 on
Blind All-in-One Image Restoration
on 5-Degradations
InTraGen: Trajectory-controlled Video Generation for Object Interactions
Advances in video generation have significantly improved the realism and quality of created scenes.
RobustFormer: Noise-Robust Pre-training for images and videos
While deep learning models are powerful tools that revolutionized many areas, they are also vulnerable to noise as they rely heavily on learning patterns and features from the exact details of the clean data.
EvenNICER-SLAM: Event-based Neural Implicit Encoding SLAM
The advancement of dense visual simultaneous localization and mapping (SLAM) has been greatly facilitated by the emergence of neural implicit representations.
ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models
This is potentially caused by limited variations in the training data and/or catastrophic forgetting, leading to domain limitations in the vision foundation models.
Autonomous Vehicle Controllers From End-to-End Differentiable Simulation
In this work, we leverage a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers on the large-scale Waymo Open Motion Dataset.
Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits
In this work, we aim to adapt CLIP for fine-grained and structured -- in the form of tabular data -- visual understanding of museum exhibits.
A Simple and Generalist Approach for Panoptic Segmentation
These contributions are: (i) a positional-embedding (PE) based loss for improved centroid regressions; (ii) Edge Distance Sampling (EDS) for the better separation of instance boundaries.
ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining
In particular, we show that (1) the distribution of the optimized GS centroids significantly differs from the uniformly sampled point cloud (used for initialization) counterpart; (2) this change in distribution results in degradation in classification but improvement in segmentation tasks when using only the centroids; (3) to leverage additional Gaussian parameters, we propose Gaussian feature grouping in a normalized feature space, along with splats pooling layer, offering a tailored solution to effectively group and embed similar Gaussians, which leads to notable improvement in finetuning tasks.
Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community
Results demonstrate the advantages of the LAE-1M dataset and the effectiveness of the LAE-DINO method.
Restore Anything Model via Efficient Degradation Adaptation
With the proliferation of mobile devices, the need for an efficient model to restore any degraded image has become increasingly significant and impactful.
Ranked #5 on
5-Degradation Blind All-in-One Image Restoration
on 5-Degradation Blind All-in-One Image Restoration
5-Degradation Blind All-in-One Image Restoration
Benchmarking
+2
iHuman: Instant Animatable Digital Humans From Monocular Videos
In this paper, we present a fast, simple, yet effective method for creating animatable 3D digital humans from monocular videos.
Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning
To answer this question, we first empirically validate that integrating MAE-based point cloud pre-training with the standard contrastive learning paradigm, even with meticulous design, can lead to a decrease in performance.
Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
Neural implicit functions have demonstrated significant importance in various areas such as computer vision, graphics.
XTrack: Multimodal Training Boosts RGB-X Video Object Trackers
Technically, we achieve this by routing samples from one modality to the expert of the others, within a mixture-of-experts framework designed for multimodal video object tracking.
Efficient Degradation-aware Any Image Restoration
Reconstructing missing details from degraded low-quality inputs poses a significant challenge.
Ranked #4 on
5-Degradation Blind All-in-One Image Restoration
on 5-Degradation Blind All-in-One Image Restoration
5-Degradation Blind All-in-One Image Restoration
Blind All-in-One Image Restoration
+1
CaLDiff: Camera Localization in NeRF via Pose Diffusion
This paper studies the problem of localizing cameras in NeRF using a diffusion model for camera pose adjustment.
Ternary-Type Opacity and Hybrid Odometry for RGB NeRF-SLAM
In this work, we address the challenge of deploying Neural Radiance Field (NeRFs) in Simultaneous Localization and Mapping (SLAM) under the condition of lacking depth information, relying solely on RGB inputs.
Diffusion-Based Particle-DETR for BEV Perception
For the enhanced safety of AVs, modeling perception uncertainty in BEV is crucial.
G-MEMP: Gaze-Enhanced Multimodal Ego-Motion Prediction in Driving
In contrast, we focus on inferring the ego trajectory of a driver's vehicle using their gaze data.
Continuous Pose for Monocular Cameras in Neural Implicit Representation
In this paper, we showcase the effectiveness of optimizing monocular camera poses as a continuous function of time.
Single-Model and Any-Modality for Video Object Tracking
In practice, most existing RGB trackers learn a single set of parameters to use them across datasets and applications.
Ranked #29 on
Rgb-T Tracking
on LasHeR
Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion Models
In this study, we introduce Lego, a textual inversion method designed to invert subject-entangled concepts from a few example images.
Model-aware 3D Eye Gaze from Weak and Few-shot Supervisions
In this work, we propose to predict 3D eye gaze from weak supervision of eye semantic segmentation masks and direct supervision of a few 3D gaze vectors.
Deformable Neural Radiance Fields using RGB and Event Cameras
In this work, we develop a novel method to model the deformable neural radiance fields using RGB and event cameras.
Prior Based Online Lane Graph Extraction from Single Onboard Camera Image
Thus, online estimation of the lane graph is crucial for widespread and reliable autonomous navigation.
Improving Online Lane Graph Extraction by Object-Lane Clustering
In this work, we propose an architecture and loss formulation to improve the accuracy of local lane graph estimates by using 3D object detection outputs.
Event-Free Moving Object Segmentation from Moving Ego Vehicle
Subsequently, we devise EmoFormer, a novel network able to exploit the event data.
Online Lane Graph Extraction from Onboard Video
One of the most common and useful representation of such an understanding is done in the form of BEV lane graphs.
NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors.
Source-free Depth for Object Pop-out
In this work, we adapt such depth inference models for object segmentation using the objects' "pop-out" prior in 3D.
Surface Normal Clustering for Implicit Representation of Manhattan Scenes
In this work, we aim to leverage the geometric prior of Manhattan scenes to improve the implicit neural radiance field representations.
Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images
On the one hand, the proposed method learns to segment these planar hulls from the labeled data.
Robust RGB-D Fusion for Saliency Detection
In this work, we aim for RGB-D saliency detection that is robust to the low-quality depths which primarily appear in two forms: inaccuracy due to noise and the misalignment to RGB.
Gradient Obfuscation Checklist Test Gives a False Sense of Security
It has since become a trend to use these five characteristics as a sufficient test, to determine whether or not gradient obfuscation is the main source of robustness.
A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials
Within the proposed benchmark, we explore some commonly known essentials of standard continual learning.
Spatially Multi-conditional Image Generation
However, multi-conditional image generation is a very challenging problem due to the heterogeneity and the sparsity of the (in practice) available conditioning labels.
Transforming Model Prediction for Tracking
Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function.
Ranked #5 on
Visual Object Tracking
on AVisT
Unsupervised Domain Adaptation for Nighttime Aerial Tracking
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications.
Collapse by Conditioning: Training Class-conditional GANs with Limited Data
On the contrary, we observe that class-conditioning causes mode collapse in limited data settings, where unconditional learning leads to satisfactory generative ability.
Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers
We use linear layers with token-consistent stochastic parameters inside the multilayer perceptron blocks, without altering the architecture of the transformer.
End-to-End Learning of Multi-category 3D Pose and Shape Estimation
We use a Transformer-based architecture to detect the keypoints, as well as to summarize the visual context of the image.
Topology Preserving Local Road Network Estimation from Single Onboard Camera Image
We represent the road topology using a set of directed lane curves and their interactions, which are captured using their intersection points.
Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images
In this work, we study the problem of extracting a directed graph representing the local road network in BEV coordinates, from a single onboard camera image.
Ranked #3 on
Lane Detection
on nuScenes
TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation
In many real-world settings, the target domain task requires a different taxonomy than the one imposed by the source domain.
GANmut: Learning Interpretable Conditional Space for Gamut of Emotions
On the other hand, learning from inexpensive and intuitive basic categorical emotion labels leads to limited emotion variability.
Rethinking Global Context in Crowd Counting
This paper investigates the role of global context for crowd counting.
Unsupervised Compound Domain Adaptation for Face Anti-Spoofing
The proposed method successfully adapts to the compound target domain consisting multiple new spoof types.
Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
Specifically, we show that: (1) our approach improves performance on all tasks when they are complementary and mutually dependent; (2) the CTRL helps to improve both semantic segmentation and depth estimation tasks performance in the challenging UDA setting; (3) the proposed ISL training scheme further improves the semantic segmentation performance.
Learning Target Candidate Association to Keep Track of What Not to Track
To tackle the problem of lacking ground-truth correspondences between distractor objects in visual tracking, we propose a training strategy that combines partial annotations with self-supervision.
Ranked #3 on
Video Object Tracking
on NT-VOT211
Unsupervised Robust Domain Adaptation without Source Data
This paper aims at answering the question of finding the right strategy to make the target model robust and accurate in the setting of unsupervised domain adaptation without source data.
Efficient Conditional GAN Transfer with Knowledge Propagation across Classes
To address this problem, we introduce a new GAN transfer method to explicitly propagate the knowledge from the old classes to the new classes.
Task Switching Network for Multi-Task Learning
Multiple tasks are performed by switching between them, performing one task at a time.
Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes
In this work, we present an unsupervised monocular framework for dense depth estimation of dynamic scenes, which jointly reconstructs rigid and non-rigid parts without explicitly modelling the camera motion.
An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement
Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain.
CompositeTasking: Understanding Images by Spatial Composition of Tasks
Learning to perform spatially distributed tasks is motivated by the frequent availability of only sparse labels across tasks, and the desire for a compact multi-tasking network.
Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation
Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains.
Soft Contrastive Learning for Visual Localization
Our soft assignment makes a gradual distinction between close and far images in both geometric and feature spaces.
Facial Emotion Recognition with Noisy Multi-task Annotations
In our formulation, we exploit a new method to enable the emotion prediction and the joint distribution learning in a unified adversarial learning game.
Learning Condition Invariant Features for Retrieval-Based Localization from 1M Images
Image features for retrieval-based localization must be invariant to dynamic objects (e. g. cars) as well as seasonal and daytime changes.
Self-Calibration Supported Robust Projective Structure-from-Motion
In this paper, we propose a unified SfM method, in which the matching process is supported by self-calibration constraints.
Geometrically Mappable Image Features
This is achieved by guiding the learning process such that the feature and geometric distances between images are directly proportional.
Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets
This paper aims at learning category-specific 3D keypoints, in an unsupervised manner, using a collection of misaligned 3D point clouds of objects from an unknown category.
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face recognition, that tries to prevent spoof attacks.
Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement
This paper introduces a divide-and-conquer inspired adversarial learning (DACAL) approach for photo enhancement.
Convex Relaxations for Consensus and Non-Minimal Problems in 3D Vision
Notably, we further exploit the POP formulation of non-minimal solver also for the generic consensus maximization problems in 3D vision.
Sliced Wasserstein Generative Models
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions.
Ranked #1 on
Video Generation
on TrailerFaces
Mapping, Localization and Path Planning for Image-based Navigation using Visual Features and Map
The problem of localization often arises as part of a navigation process.
Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANs
Furthermore, we introduce a sliced version of Wasserstein GAN (SWGAN) loss to improve the distribution learning on the video data of high-dimension and mixed-spatiotemporal distribution.
Sampling Algebraic Varieties for Robust Camera Autocalibration
This paper addresses the problem of robustly autocalibrating a moving camera with constant intrinsics.
Incremental Non-Rigid Structure-from-Motion with Unknown Focal Length
In this paper we present a method for incremental Non-Rigid Structure-from-Motion (NRSfM) with the perspective camera model and the isometric surface prior with unknown focal length.
Model-free Consensus Maximization for Non-Rigid Shapes
In this paper, we formulate the model-free consensus maximization as an Integer Program in a graph using `rules' on measurements.
Face Translation between Images and Videos using Identity-aware CycleGAN
This paper presents a new problem of unpaired face translation between images and videos, which can be applied to facial video prediction and enhancement.
Improving Video Generation for Multi-functional Applications
In this paper, we aim to improve the state-of-the-art video generative adversarial networks (GANs) with a view towards multi-functional applications.
Optimal Transformation Estimation With Semantic Cues
This paper addresses the problem of estimating the geometric transformation relating two distinct visual modalities (e. g. an image and a map, or a projective structure and a Euclidean 3D model) while relying only on semantic cues, such as semantically segmented regions or object bounding boxes.
Consensus Maximization With Linear Matrix Inequality Constraints
While randomized methods like RANSAC are fast, they do not guarantee global optimality and fail to manage large amounts of outliers.
Sliced Wasserstein Generative Models
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions.
Robust and Optimal Sum-of-Squares-Based Point-to-Plane Registration of Image Sets and Structured Scenes
This paper deals with the problem of registering a known structured 3D scene and its metric Structure-from-Motion (SfM) counterpart.
LMI-Based 2D-3D Registration: From Uncalibrated Images to Euclidean Scene
This paper investigates the problem of registering a scanned scene, represented by 3D Euclidean point coordinates, and two or more uncalibrated cameras.
Efficient Pruning LMI Conditions for Branch-and-Prune Rank and Chirality-Constrained Estimation of the Dual Absolute Quadric
We present a new globally optimal algorithm for self-calibrating a moving camera with constant parameters.
